A Review: AI and Computer Vision in Ovarian Cancer Detection (2023)

Four years ago, there were a few relatively primitive studies about utilising AI in Cancer detection. Back then, the technology was nowhere as it is now.

In 2020, my mother died relatively suddenly. We found out after she died that she had a malignant mixed Müllerian tumor (MMMT). This kind of cancer can be found in the uterus, the ovaries, fallopian tubes, and cervix.

The diagnosis of this kind of ovarian cancer is extremely low — most women are NOT diagnosed until stage four, when survival is only at 3% over five years.

This is absolutely a horror story for women over 40. My mom didn’t have any of the risk factors. Late diagnosis of these types of cancers are costing hospitals in the UK 100,000 deaths per year, according to 2009 statistics on epidemiology.

According to the NIH:

“Carcinosarcomas of the uterus (womb) are uncommon cancers accounting for 4.3% of all cancers of the womb. These rare cancers have poor prognosis; one of the reasons for the poor survival outcome is the fact that over a third of these cancers (carcinosarcomas) have already spread beyond the womb at the time of diagnosis.”

Late diagnosis is the silent killer here.

With AI and computer vision, early diagnosis is possible.

If AI can successfully identify a taxicab in an image — It can also detect unusual cancerous cells with the right training. See the images below for what this looks like. The example I show below is in LUNG cancer, but this technology can be applied to many different kinds of cancer.

A study done in Japan showed 80% accuracy for certain models to predict ovarian tumors. This accuracy level is going to improve over time as models continue to improve according to Moore’s law of computing.

The study also theorizes that with the implementation of wide spread colposcopies in women over the age of 40, utilising AI, we can diagnose 93% of ovarian cancers before they cause significant damage to patients.

Conclusion

In summary, there needs to be more research and development (Further study) on these models, but with the rapid advancement of medical science and AI technology, we are getting closer to our goal as a society: stopping cancer.

Disclaimer: This article contains sponsored marketing content. It is intended for promotional purposes and should not be considered as an endorsement or recommendation by our website. Readers are encouraged to conduct their own research and exercise their own judgment before making any decisions based on the information provided in this article.